English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous navigation in crowded environments is an open problem with manyapplications, essential for the coexistence of robots and humans in the smartcities of the future. In recent years, deep reinforcement learning approacheshave proven to outperform model-based algorithms. Nevertheless, even though theresults provided are promising, the works are not able to take advantage of thecapabilities that their models offer. They usually get trapped in local optimain the training process, that prevent them from learning the optimal policy.They are not able to visit and interact with every possible stateappropriately, such as with the states near the goal or near the dynamicobstacles. In this work, we propose using intrinsic rewards to balance betweenexploration and exploitation and explore depending on the uncertainty of thestates instead of on the time the agent has been trained, encouraging the agentto get more curious about unknown states. We explain the benefits of theapproach and compare it with other exploration algorithms that may be used forcrowd navigation. Many simulation experiments are performed modifying severalalgorithms of the state-of-the-art, showing that the use of intrinsic rewardsmakes the robot learn faster and reach higher rewards and success rates (fewercollisions) in shorter navigation times, outperforming the state-of-the-art.

Improving robot navigation in crowded environments using intrinsic rewards